Sync test results from your IDE to the Invarium dashboard. After running test cases locally, use this tool to upload the results. Creates a new test run or appends to an existing one. This tool is called automatically during test execution. No user confirmation is needed. For streaming mode, ca...
Part of the Invarium MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents invoke invarium_sync_results to trigger processes or run actions in Invarium. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
invarium_sync_results can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
tools:
invarium_sync_results:
rules:
- action: allow
rate_limit:
max: 10
window: 60
validate:
required_args: trueSee the full Invarium policy for all 19 tools.
Agents calling execute-class tools like invarium_sync_results have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Execute risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
invarium_sync_results is one of the high-risk operations in Invarium. For the full severity-focused view — only the high-risk tools with their recommended policies — see the breakdown for this server, or browse all high-risk tools across every MCP server.
Sync test results from your IDE to the Invarium dashboard. After running test cases locally, use this tool to upload the results. Creates a new test run or appends to an existing one. This tool is called automatically during test execution. No user confirmation is needed. For streaming mode, call with create_empty=True first to get the dashboard link, then stream results as tests complete. WHEN TO USE: Automatically called during test execution setup (create_empty=True) and by the trace library during test runs. AFTER THIS: Show the test run link. Then fetch analytics with invarium_get_test_run and invarium_get_agent to present pass rate, AQS score, and intelligent next-step recommendations. For streaming test execution: call with create_empty=True and results="[]" to create an empty test run. Returns test_run_id + dashboard URL. Then run the test script in the background — it streams results to the MCP server one at a time. Args: agent_name: Name of the agent whose tests were run. results: JSON array of test result objects. Each must contain: scenario_id (string) — ID of the test case. user_message (string) — The input sent to the agent. agent_response (string) — The agent's actual output. Optional: tools_called (array of objects, each with required 'name' and optional 'parameters'), passed (boolean), notes (string), latency_ms (number — execution time in milliseconds), error_message (string — error details for failed cases). test_run_id: Optional existing test run ID for incremental sync. If provided, results are appended to that run. If omitted, a new test run is created. name: Optional human-readable name for the test run (e.g. "Smoke Test — Mixed Complexity"). Helps identify runs on the dashboard. source: Label for where tests were executed. Valid values: "mcp", "ci", "vscode", "cli", "api" (default: "mcp"). create_empty: If True, create an empty test run with no results. Returns test_run_id + dashboard URL for streaming mode. The results parameter is ignored when this is True. expected_total: Expected number of test results for streaming mode. Tells the backend how many results to expect before marking the run as completed. Use with create_empty=True. Returns: A summary string with test run ID and dashboard link on success, or an error message on failure.. It is categorised as a Execute tool in the Invarium MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Add a rule in your Intercept YAML policy under the tools section for invarium_sync_results. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Invarium MCP server.
invarium_sync_results is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the invarium_sync_results rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for invarium_sync_results. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
invarium_sync_results is provided by the Invarium MCP server (invarium-ai/invarium). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept